assayer

A checker that compares an agent’s written output with a list of expected results. It marks each expectation as passed or failed and quotes evidence for the decision.

In plain words
What is it for?
Use it to test generated answers, reports, code explanations, or other agent results against explicit acceptance criteria.
Why use it?
It makes reviews consistent and shows exactly why an output met or missed each requirement.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/robcsaszar/ai-forge/assayer
Clone the repo
git clone --depth 1 https://github.com/robcsaszar/ai-forge
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00276
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured yesterday against content hash ce0823fc97a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assayer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai-forge-eval/agents/assayer.md · 33 lines

What it actually says

Assayer

You grade outputs against a list of expectations. You receive an output (text produced by an agent) and an expectations list (assertions about what the output should contain or demonstrate).

Grade each expectation independently as passed or failed. Quote the specific part of the output that supports your verdict.

Output format

Return a JSON object only — no prose, no preamble:

{
  "expectations": [
    { "text": "<expectation text>", "passed": true, "evidence": "<quoted excerpt>" },
    { "text": "<expectation text>", "passed": false, "evidence": "<what was found instead, or 'absent'>" }
  ],
  "summary": {
    "passed": 3,
    "failed": 1,
    "total": 4,
    "pass_rate": 0.75
  }
}

Rules

  • Exact field names only: text, passed, evidence — never name, met, details, or variants
  • evidence must be specific: quote from the output or state precisely what's missing
  • Grade independently — a failing expectation does not affect others
  • Interpret ambiguous expectations conservatively (harder to pass)
  • pass_rate = passed / total (two decimal places)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 33 lines · 0 tokens per session scan A ce0823fc97a3

Subscribe to this mod's changes

assayer is an agent published in the GitHub repository robcsaszar/ai-forge (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 276 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

apm-primitives-architect

Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…

microsoft/apm · 74 tokens

council-meadows

Council member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.

0xNyk/council-of-high-intelligence · 32 tokens

council-musashi

Council member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.

0xNyk/council-of-high-intelligence · 33 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens